Name: mempalace-recall
Rating: 66.4 (1 reviews)
Author: MemPalace

mempalace-recall

Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall is invoked. Complements the mempalace setup skill and requires the mempalace-mcp server.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/mempalace-recall/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, actionable recall protocol with a clear tool-selection table, sequenced steps, and thorough error-recovery guidance. It is efficient and appropriately points to canonical external protocols for full detail, with only minor gaps in inline validation and a missing worked example call.

Suggestions

Trim the 'Act as a senior AI-memory systems engineer...' identity persona line, which restates expertise Claude already assumes, to tighten conciseness.

Add one short worked example of a primary recall call (e.g. `mempalace_search(query="who decided on the auth approach", limit=5)`) to lift actionability from mostly-executable to fully copy-paste ready.

Make the main protocol's validation explicit by adding an inline checkpoint before returning verbatim (e.g. 'If search returns nothing, say so and offer to widen — do not proceed to answer from model memory').

Dimension	Reasoning	Score
Conciseness	The body is largely efficient — a tool-selection table, numbered protocol, and tight anti-pattern list — with only minor trims possible, chiefly the "Act as a senior AI-memory systems engineer..." persona line and a few justifying clauses; it does not over-explain concepts Claude already knows.	4 / 5
Actionability	Concrete, executable guidance throughout: a tool-selection table mapping needs to specific MCP tools, named tool calls in the protocol, and copy-paste-ready repair commands; the minor gap is the absence of a full example call showing arguments for the primary `mempalace_search` operation.	4 / 5
Workflow Clarity	The Protocol is a clearly sequenced 6-step list, and the Unhappy paths section provides feedback loops for error recovery (empty results, MCP error, corrupt index with `mempalace repair-status` verification, conflicting facts); it falls short of 5 because inline validation checkpoints in the main flow are mostly implicit rather than explicit.	4 / 5
Progressive Disclosure	Well-organized into clear sections with well-signaled, one-level-deep references to canonical published protocols (recall-protocol.md, coordination-protocol.md); no local bundle files exist to split, and the SKILL.md correctly stays an overview, though some inlined detail (e.g. the full corrupt-index recovery) keeps it just shy of the ideal split.	4 / 5
	Total	16 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it explicitly answers both what the skill does and when to apply it using natural trigger phrases, and clearly distinguishes itself from the sibling mempalace setup skill. The only mild gap is specificity, limited by the skill's inherently single-purpose nature.

Dimension	Reasoning	Score
Specificity	Names the domain and one core concrete action ("search the palace before answering about past work, people, projects, or prior decisions"), but the skill is single-purpose so it does not list multiple distinct actions; this matches the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	Clearly states what ("Recall protocol for MemPalace — search the palace before answering...") and an explicit "Apply when..." clause with concrete trigger phrases, matching the anchor that requires both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Strong natural trigger phrases a user would actually say ("what was decided", "what happened before", "who someone is", "what was discussed last time") with good variation, though a few synonyms are absent and no file-extension-style terms apply to this domain.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (recall only) and explicitly carves the boundary ("Complements the mempalace setup skill and requires the mempalace-mcp server"), giving it distinct triggers with minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MemPalace/mempalace
Path: skills/mempalace-recall/SKILL.md
Commit: 5ea40d3

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.